| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20130927091427.GE24743@yliu-dev.sh.intel.com>
Date: Fri, 27 Sep 2013 17:14:27 +0800
From: Yuanhan Liu <yuanhan.liu@...ux.intel.com>
To: peterz@...radead.org
Cc: mingo@...nel.org, hpa@...or.com, linux-kernel@...r.kernel.org,
tglx@...utronix.de, linux-tip-commits@...r.kernel.org,
Fengguang Wu <fengguang.wu@...el.com>,
Huang Ying <ying.huang@...el.com>, lkp@...ux.intel.com,
Yuanhan Liu <yuanhan.liu@...ux.intel.com>
Subject: Re: [tip:sched/core] sched: Add NEED_RESCHED to the preempt_count
On Wed, Sep 25, 2013 at 09:38:38AM -0700, tip-bot for Peter Zijlstra wrote:
> Commit-ID: f27dde8deef33c9e58027df11ceab2198601d6a6
> Gitweb: http://git.kernel.org/tip/f27dde8deef33c9e58027df11ceab2198601d6a6
> Author: Peter Zijlstra <peterz@...radead.org>
> AuthorDate: Wed, 14 Aug 2013 14:55:31 +0200
> Committer: Ingo Molnar <mingo@...nel.org>
> CommitDate: Wed, 25 Sep 2013 14:07:49 +0200
>
> sched: Add NEED_RESCHED to the preempt_count
Hi Peter,
FYI, here we found a pigz regression by this commit.
Here is a list all of changed stats by this commit and it's parent 4a2b4b222743bb07fedf985b884550f2ca067ea9:
f27dde8deef33c9e58027df11ce 4a2b4b222743bb07fedf985b884
pigz.throughput [ 1.3953 - 2.4574 ] [ 391.49 - 392.43 ]
vmstat.cpu.id [ 99 - 99 ] [ 11 - 12 ]
vmstat.system.cs [ 968 - 1159 ] [ 63025 - 63666 ]
iostat.cpu.user [ 0.28527 - 0.51661 ] [ 86.299 - 86.544 ]
time.user_time [ 196.66 - 280.86 ] [ 16712 - 16759 ]
time.percent_of_cpu_this_job_got [ 124 - 143 ] [ 5642 - 5658 ]
time.elapsed_time [ 338.69 - 398.91 ] [ 300.2 - 300.23 ]
time.involuntary_context_switches [ 3184 - 4753 ] [ 5.536e+05 - 5.9042e+05 ]
time.voluntary_context_switches [ 84559 - 1.2223e+05 ] [ 1.1008e+07 - 1.1092e+07 ]
lock_stat.clockevents_lock.contentions [ 1.4125e+05 - 1.6922e+05 ] [ 1.6487e+06 - 1.679e+06 ]
lock_stat.clockevents_lock.contentions.clockevents_notify [ 2.8253e+05 - 3.3844e+05 ] [ 3.2975e+06 - 3.358e+06 ]
lock_stat.&pipe->mutex/1.contentions.pipe_write [ 2533 - 3198 ] [ 27814 - 28802 ]
lock_stat.jiffies_lock.contentions.tick_do_update_jiffies64 [ 1008 - 1822 ] [ 31272 - 33448 ]
lock_stat.jiffies_lock.contentions [ 504 - 911 ] [ 15636 - 16724 ]
iostat.cpu.idle [ 99.217 - 99.446 ] [ 12.081 - 12.271 ]
lock_stat.&rq->lock.contentions [ 7878 - 9593 ] [ 1.7954e+05 - 1.8646e+05 ]
lock_stat.rcu_node_1.contentions.force_qs_rnp [ 2200 - 2564 ] [ 33544 - 35368 ]
lock_stat.&(&futex_queues[i].lock)->rlock.contentions.futex_wake [ 9993 - 16537 ] [ 1.3794e+06 - 1.4482e+06 ]
lock_stat.rcu_node_1.contentions [ 7854 - 9260 ] [ 2.4984e+05 - 2.6247e+05 ]
lock_stat.&(&futex_queues[i].lock)->rlock.contentions [ 8779 - 14582 ] [ 1.2373e+06 - 1.301e+06 ]
lock_stat.&pipe->mutex/1.contentions [ 3572 - 4125 ] [ 1.4362e+05 - 1.507e+05 ]
lock_stat.rcu_node_1.contentions.rcu_process_callbacks [ 9511 - 11254 ] [ 4.5502e+05 - 4.7776e+05 ]
lock_stat.&pipe->mutex/1.contentions.pipe_read [ 2163 - 2683 ] [ 1.3208e+05 - 1.3934e+05 ]
vmstat.system.in [ 713 - 799 ] [ 27310 - 27526 ]
lock_stat.&pipe->mutex/1.contentions.pipe_lock_nested [ 1802 - 2219 ] [ 1.2618e+05 - 1.334e+05 ]
lock_stat.&(&futex_queues[i].lock)->rlock.contentions.futex_wait_setup [ 6447 - 10781 ] [ 9.3156e+05 - 9.9482e+05 ]
iostat.cpu.system [ 0.25493 - 0.29317 ] [ 1.3752 - 1.4608 ]
vmstat.cpu.us [ 0 - 0 ] [ 86 - 86 ]
lock_stat.&rq->lock.contentions.try_to_wake_up [ 4928 - 6018 ] [ 1.1351e+05 - 1.5691e+05 ]
lock_stat.&rq->lock.contentions.__schedule [ 3036 - 3658 ] [ 81508 - 1.3994e+05 ]
lock_stat.&(&futex_queues[i].lock)->rlock/1.contentions.futex_requeue [ 57 - 114 ] [ 9139 - 16865 ]
lock_stat.&(&futex_queues[i].lock)->rlock/1.contentions [ 57 - 114 ] [ 9135 - 16860 ]
lock_stat.&(&futex_queues[i].lock)->rlock/1.contentions.futex_wait_setup [ 55 - 100 ] [ 8253 - 15331 ]
lock_stat.&(&futex_queues[i].lock)->rlock.contentions.futex_requeue [ 753 - 1810 ] [ 83288 - 1.6982e+05 ]
time.minor_page_faults [ 66817 - 67950 ] [ 69059 - 69092 ]
And here are text plots for above stats:
O for 4a2b4b222743bb07fedf985b884550f2ca067ea9
* for f27dde8deef33c9e58027df11ceab2198601d6a6
pigz.throughput
400 O+------O------O-------O-------O------O-------O-------O------O-------O
| |
350 ++ |
300 ++ |
| |
250 ++ |
| |
200 ++ |
| |
150 ++ |
100 ++ |
| |
50 ++ |
| |
0 *+------*------*-------*-------*------*-------*-------*------*-------*
time.user_time
18000 ++-----------------------------------------------------------------+
O O O O O O O O O O
16000 ++ |
14000 ++ |
| |
12000 ++ |
10000 ++ |
| |
8000 ++ |
6000 ++ |
| |
4000 ++ |
2000 ++ |
| |
0 *+-----*-------*------*-------*------*-------*------*-------*------*
time.percent_of_cpu_this_job_got
6000 ++------------------------------------------------------------------+
O O O O O O O O O O
5000 ++ |
| |
| |
4000 ++ |
| |
3000 ++ |
| |
2000 ++ |
| |
| |
1000 ++ |
| |
0 *+------*------*-------*------*-------*------*-------*------*-------*
time.elapsed_time
400 ++------*--------------*---------------------------------------------+
390 ++ ... . .. .. |
| .. . .. . |
380 *+ .. . . |
370 ++ .. .. |
| * ..*.. |
360 ++ *..... .... .. |
350 ++ . ....*. .. |
340 ++ *... |
| *.......*
330 ++ |
320 ++ |
| |
310 ++ |
300 O+------O------O-------O-------O------O-------O-------O------O-------O
time.minor_page_faults
69500 ++-----------------------------------------------------------------+
| O O O O O O O O
69000 O+ O |
68500 ++ |
| |
68000 ++ ....*......*..... ...*
*......*... .. .*. *... |
67500 ++ *..... ... . .. |
| . .. .. . |
67000 ++ *. . . |
66500 ++ . .. |
| . |
66000 ++ * |
| |
65500 ++-----------------------------------------------------------------+
time.voluntary_context_switches
1.2e+07 ++---------------------------------------------------------------+
O O O O O O O O O O
1e+07 ++ |
| |
| |
8e+06 ++ |
| |
6e+06 ++ |
| |
4e+06 ++ |
| |
| |
2e+06 ++ |
| |
0 *+-----*------*-------*------*------*------*-------*------*------*
time.involuntary_context_switches
700000 ++----------------------------------------------------------------+
| |
600000 O+ O O |
| O O O O O O O
500000 ++ |
| |
400000 ++ |
| |
300000 ++ |
| |
200000 ++ |
| |
100000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
vmstat.system.in
30000 ++-----------------------------------------------------------------+
O O O O O O O O O O
25000 ++ |
| |
| |
20000 ++ |
| |
15000 ++ |
| |
10000 ++ |
| |
| |
5000 ++ |
| |
0 *+-----*-------*------*-------*------*-------*------*-------*------*
vmstat.system.cs
70000 ++-----------------------------------------------------------------+
O O O O O O O O O O
60000 ++ |
| |
50000 ++ |
| |
40000 ++ |
| |
30000 ++ |
| |
20000 ++ |
| |
10000 ++ |
| |
0 *+-----*-------*------*-------*------*-------*------*-------*------*
vmstat.cpu.us
90 ++--------------------------------------------------------------------+
O O O O O O O O O O
80 ++ |
70 ++ |
| |
60 ++ |
50 ++ |
| |
40 ++ |
30 ++ |
| |
20 ++ |
10 ++ |
| |
0 *+------*-------*------*-------*-------*-------*------*-------*-------*
vmstat.cpu.id
100 *+------*------*-------*-------*------*-------*-------*------*-------*
| |
90 ++ |
80 ++ |
| |
70 ++ |
60 ++ |
| |
50 ++ |
40 ++ |
| |
30 ++ |
20 ++ |
| |
10 O+------O------O-------O-------O------O-------O-------O------O-------O
lock_stat.clockevents_lock.contentions
1.8e+06 ++---------------------------------------------------------------+
O O O O O O O O O O
1.6e+06 ++ |
1.4e+06 ++ |
| |
1.2e+06 ++ |
1e+06 ++ |
| |
800000 ++ |
600000 ++ |
| |
400000 ++ |
200000 ++ |
*......*......*.......*......*......*......*.......*......*......*
0 ++---------------------------------------------------------------+
lock_stat.clockevents_lock.contentions.clockevents_notify
3.5e+06 ++---------------------------------------------------------------+
O O O O O O O O O O
3e+06 ++ |
| |
2.5e+06 ++ |
| |
2e+06 ++ |
| |
1.5e+06 ++ |
| |
1e+06 ++ |
| |
500000 ++ |
*......*......*.......*......*......*......*.......*......*......*
0 ++---------------------------------------------------------------+
lock_stat.&rq->lock.contentions
200000 ++----------------------------------------------------------------+
180000 O+ O O O O O O O O |
| O
160000 ++ |
140000 ++ |
| |
120000 ++ |
100000 ++ |
80000 ++ |
| |
60000 ++ |
40000 ++ |
| |
20000 *+.....*.......*......*......*.......*......*......*.......*......*
0 ++----------------------------------------------------------------+
lock_stat.&rq->lock.contentions.try_to_wake_up
160000 ++-------------O---------------------O----------------------------+
| |
140000 ++ |
120000 ++ O O O O |
O O O
100000 ++ |
| |
80000 ++ |
| |
60000 ++ O |
40000 ++ |
| |
20000 ++ |
| ...*.......*...... ...*....... ...*
0 *+--------------------*------*-------*------*--------------*------+
lock_stat.&rq->lock.contentions.__schedule
160000 O+----------------------------------------------------------------+
| |
140000 ++ O |
120000 ++ O |
| |
100000 ++ O O O O
| |
80000 ++ O O O |
| |
60000 ++ |
40000 ++ |
| |
20000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.&(&futex_queues[i].lock)->rlock.contentions
1.4e+06 ++---------------------------------------------------------------+
O O O O O O O O
1.2e+06 ++ O O |
| |
1e+06 ++ |
| |
800000 ++ |
| |
600000 ++ |
| |
400000 ++ |
| |
200000 ++ |
| |
0 *+-----*------*-------*------*------*------*-------*------*------*
lock_stat.&(&futex_queues[i].lock)->rlock.contentions.futex_wake
1.6e+06 ++---------------------------------------------------------------+
O O O O O
1.4e+06 ++ O O O O O |
| |
1.2e+06 ++ |
1e+06 ++ |
| |
800000 ++ |
| |
600000 ++ |
400000 ++ |
| |
200000 ++ |
| |
0 *+-----*------*-------*------*------*------*-------*------*------*
lock_stat.&(&futex_queues[i].lock)->rlock.contentions.futex_wait_setup
1.2e+06 ++---------------------------------------------------------------+
| |
1e+06 ++ O O |
O O O O O O O O
| |
800000 ++ |
| |
600000 ++ |
| |
400000 ++ |
| |
| |
200000 ++ |
| |
0 *+-----*------*-------*------*------*------*-------*------*------*
lock_stat.&(&futex_queues[i].lock)->rlock.contentions.futex_requeue
180000 ++----------------------------------------------------------------+
O O O O O
160000 ++ O |
140000 ++ |
| O |
120000 ++ |
100000 ++ O |
| |
80000 ++ O O |
60000 ++ |
| |
40000 ++ |
20000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.rcu_node_1.contentions
300000 ++----------------------------------------------------------------+
| |
250000 O+ O O O O O O O O
| O |
| |
200000 ++ |
| |
150000 ++ |
| |
100000 ++ |
| |
| |
50000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.rcu_node_1.contentions.rcu_process_callbacks
500000 ++----------------------------------------------------------------+
450000 O+ O O O O O O O O O
| |
400000 ++ |
350000 ++ |
| |
300000 ++ |
250000 ++ |
200000 ++ |
| |
150000 ++ |
100000 ++ |
| |
50000 ++ |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.rcu_node_1.contentions.force_qs_rnp
40000 ++-----------------------------------------------------------------+
| |
35000 O+ O O O O O O O O
30000 ++ O |
| |
25000 ++ |
| |
20000 ++ |
| |
15000 ++ |
10000 ++ |
| |
5000 ++ |
*......*.......*......*.......*......*.......*......*.......*......*
0 ++-----------------------------------------------------------------+
lock_stat.&pipe->mutex/1.contentions
160000 ++-----------------------------------O----------------------------+
| O O O O O O O O
140000 O+ |
120000 ++ |
| |
100000 ++ |
| |
80000 ++ |
| |
60000 ++ |
40000 ++ |
| |
20000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.&pipe->mutex/1.contentions.pipe_lock_nested
140000 ++-----------------------------------O----------------------------+
O O O O O O O O O
120000 ++ |
| |
100000 ++ |
| |
80000 ++ |
| |
60000 ++ |
| |
40000 ++ |
| |
20000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.&pipe->mutex/1.contentions.pipe_read
160000 ++----------------------------------------------------------------+
| O |
140000 ++ O O O O O O O O
120000 O+ |
| |
100000 ++ |
| |
80000 ++ |
| |
60000 ++ |
40000 ++ |
| |
20000 ++ |
| |
0 *+-----*-------*------*------*-------*------*------*-------*------*
lock_stat.&pipe->mutex/1.contentions.pipe_write
30000 ++-----------------------------------------------------------------+
O O O O O O O O O O
25000 ++ |
| |
| |
20000 ++ |
| |
15000 ++ |
| |
10000 ++ |
| |
| |
5000 ++ ...*....... |
*......*.......*......*.......*......*.......*... *......*
0 ++-----------------------------------------------------------------+
lock_stat.jiffies_lock.contentions
18000 ++-----------------------------------------------------------------+
O O O O O O |
16000 ++ O O O O
14000 ++ |
| |
12000 ++ |
10000 ++ |
| |
8000 ++ |
6000 ++ |
| |
4000 ++ |
2000 ++ |
*......*....... ...*....... ...*....... ...*.......*......*
0 ++-------------*--------------*--------------*---------------------+
lock_stat.jiffies_lock.contentions.tick_do_update_jiffies64
35000 ++-----------------------------------------------------------------+
O O O O O O O O O
30000 ++ O |
| |
25000 ++ |
| |
20000 ++ |
| |
15000 ++ |
| |
10000 ++ |
| |
5000 ++ |
*......*.......*......*....... ...*....... ...*.......*......*
0 ++----------------------------*--------------*---------------------+
lock_stat.&(&futex_queues[i].lock)->rlock/1.contentions
18000 ++-----------------------------------------------------------------+
| O O |
16000 ++ |
14000 O+ O |
| O |
12000 ++ O O |
10000 ++ O
| O |
8000 ++ O |
6000 ++ |
| |
4000 ++ |
2000 ++ |
| |
0 *+-----*-------*------*-------*------*-------*------*-------*------*
lock_stat.&(&futex_queues[i].lock)->rlock/1.contentions.futex_requeue
18000 ++-----------------------------------------------------------------+
| O O |
16000 ++ |
14000 O+ O O |
| |
12000 ++ O O |
10000 ++ O
| O |
8000 ++ O |
6000 ++ |
| |
4000 ++ |
2000 ++ |
| |
0 *+-----*-------*------*-------*------*-------*------*-------*------*
lock_stat.&(&futex_queues[i].lock)->rlock/1.contentions.futex_wait_setup
16000 ++-------------O---------------------------------------------------+
| O |
14000 O+ |
12000 ++ O |
| |
10000 ++ O O O
| O |
8000 ++ O O |
| |
6000 ++ |
4000 ++ |
| |
2000 ++ |
| |
0 *+-----*-------*------*-------*------*-------*------*-------*------*
iostat.cpu.user
90 ++--------------------------------------------------------------------+
O O O O O O O O O O
80 ++ |
70 ++ |
| |
60 ++ |
50 ++ |
| |
40 ++ |
30 ++ |
| |
20 ++ |
10 ++ |
| |
0 *+------*-------*------*-------*-------*-------*------*-------*-------*
iostat.cpu.system
1.6 ++-------------------------------------------------------------------+
| O O O |
1.4 O+ O O O O O O
| |
1.2 ++ |
| |
1 ++ |
| |
0.8 ++ |
| |
0.6 ++ |
| |
0.4 ++ |
*.......*......*.......*.......*......*.......*.......*...... ....*
0.2 ++-----------------------------------------------------------*-------+
iostat.cpu.idle
100 *+------*------*-------*-------*------*-------*-------*------*-------*
| |
90 ++ |
80 ++ |
| |
70 ++ |
60 ++ |
| |
50 ++ |
40 ++ |
| |
30 ++ |
20 ++ |
| |
10 O+------O------O-------O-------O------O-------O-------O------O-------O
And here is the bisect log:
---
:040000 040000 138132af1aff14d343d8355837e7f98b6e92cfe1 333aa1c56d624a9991ba13cef1dc08b9976d666a M include
:040000 040000 b47be033e17c9dc558db7bdd3fab1a67b5a8596d 3ba4f3b71ee73a57f09204cba4247133479c12b6 M kernel
bisect run success
# bad: [62a27650cea1a65e4b951d0b58d089c9d206b2d7] Merge remote-tracking branch 'radeon-alex/drm-fixes-3.12' into kbuild_tmp
# good: [272b98c6455f00884f0350f775c5342358ebb73f] Linux 3.12-rc1
git bisect start '62a27650cea1a65e4b951d0b58d089c9d206b2d7' '272b98c6455f00884f0350f775c5342358ebb73f' '--'
# good: [d0060a777b3d1fd37bdeeabbc6af4a177fa1ad6d] drm/i915: clean up and simplify i9xx_crtc_mode_set wrt PLL handling
git bisect good d0060a777b3d1fd37bdeeabbc6af4a177fa1ad6d
# good: [57a42192e61e7d0074fa6027e2565461bfd60147] staging: dgap: driver.c: removes smatch warning "redundant null check"
git bisect good 57a42192e61e7d0074fa6027e2565461bfd60147
# bad: [d2d55f430eac6bd20dcb3b8b11bfb3018d3fadef] Merge remote-tracking branch 'arm-perf/aarch64' into kbuild_tmp
git bisect bad d2d55f430eac6bd20dcb3b8b11bfb3018d3fadef
# bad: [324f7d868098d2fc547f9b76a77a610d53ca61b5] Merge remote-tracking branch 'smack/next' into kbuild_tmp
git bisect bad 324f7d868098d2fc547f9b76a77a610d53ca61b5
# bad: [1a338ac32ca630f67df25b4a16436cccc314e997] sched, x86: Optimize the preempt_schedule() call
git bisect bad 1a338ac32ca630f67df25b4a16436cccc314e997
# good: [f48627e686a69f5215cb0761e731edb3d9859dd9] sched/balancing: Periodically decay max cost of idle balance
git bisect good f48627e686a69f5215cb0761e731edb3d9859dd9
# good: [4a2b4b222743bb07fedf985b884550f2ca067ea9] sched: Introduce preempt_count accessor functions
git bisect good 4a2b4b222743bb07fedf985b884550f2ca067ea9
# bad: [01028747559ac6c6f642a7bbd2875cc4f66b2feb] sched: Create more preempt_count accessors
git bisect bad 01028747559ac6c6f642a7bbd2875cc4f66b2feb
# bad: [a787870924dbd6f321661e06d4ec1c7a408c9ccf] sched, arch: Create asm/preempt.h
git bisect bad a787870924dbd6f321661e06d4ec1c7a408c9ccf
# bad: [f27dde8deef33c9e58027df11ceab2198601d6a6] sched: Add NEED_RESCHED to the preempt_count
git bisect bad f27dde8deef33c9e58027df11ceab2198601d6a6
# first bad commit: [f27dde8deef33c9e58027df11ceab2198601d6a6] sched: Add NEED_RESCHED to the preempt_count
Please feel free to ask more data if necessary.
Thanks.
--yliu
>
> In order to combine the preemption and need_resched test we need to
> fold the need_resched information into the preempt_count value.
>
> Since the NEED_RESCHED flag is set across CPUs this needs to be an
> atomic operation, however we very much want to avoid making
> preempt_count atomic, therefore we keep the existing TIF_NEED_RESCHED
> infrastructure in place but at 3 sites test it and fold its value into
> preempt_count; namely:
>
> - resched_task() when setting TIF_NEED_RESCHED on the current task
> - scheduler_ipi() when resched_task() sets TIF_NEED_RESCHED on a
> remote task it follows it up with a reschedule IPI
> and we can modify the cpu local preempt_count from
> there.
> - cpu_idle_loop() for when resched_task() found tsk_is_polling().
>
> We use an inverted bitmask to indicate need_resched so that a 0 means
> both need_resched and !atomic.
>
> Also remove the barrier() in preempt_enable() between
> preempt_enable_no_resched() and preempt_check_resched() to avoid
> having to reload the preemption value and allow the compiler to use
> the flags of the previuos decrement. I couldn't come up with any sane
> reason for this barrier() to be there as preempt_enable_no_resched()
> already has a barrier() before doing the decrement.
>
> Suggested-by: Ingo Molnar <mingo@...nel.org>
> Signed-off-by: Peter Zijlstra <peterz@...radead.org>
> Link: http://lkml.kernel.org/n/tip-7a7m5qqbn5pmwnd4wko9u6da@git.kernel.org
> Signed-off-by: Ingo Molnar <mingo@...nel.org>
> ---
> include/linux/preempt.h | 47 ++++++++++++++++++++++++++++++++++++++++++-----
> include/linux/sched.h | 7 +++++--
> kernel/cpu/idle.c | 7 +++++++
> kernel/sched/core.c | 20 +++++++++++++++-----
> 4 files changed, 69 insertions(+), 12 deletions(-)
>
> diff --git a/include/linux/preempt.h b/include/linux/preempt.h
> index eaac52a..92e3418 100644
> --- a/include/linux/preempt.h
> +++ b/include/linux/preempt.h
> @@ -10,9 +10,19 @@
> #include <linux/linkage.h>
> #include <linux/list.h>
>
> +/*
> + * We use the MSB mostly because its available; see <linux/preempt_mask.h> for
> + * the other bits -- can't include that header due to inclusion hell.
> + */
> +#define PREEMPT_NEED_RESCHED 0x80000000
> +
> +/*
> + * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
> + * that think a non-zero value indicates we cannot preempt.
> + */
> static __always_inline int preempt_count(void)
> {
> - return current_thread_info()->preempt_count;
> + return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
> }
>
> static __always_inline int *preempt_count_ptr(void)
> @@ -20,11 +30,40 @@ static __always_inline int *preempt_count_ptr(void)
> return ¤t_thread_info()->preempt_count;
> }
>
> +/*
> + * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
> + * alternative is loosing a reschedule. Better schedule too often -- also this
> + * should be a very rare operation.
> + */
> static __always_inline void preempt_count_set(int pc)
> {
> *preempt_count_ptr() = pc;
> }
>
> +/*
> + * We fold the NEED_RESCHED bit into the preempt count such that
> + * preempt_enable() can decrement and test for needing to reschedule with a
> + * single instruction.
> + *
> + * We invert the actual bit, so that when the decrement hits 0 we know we both
> + * need to resched (the bit is cleared) and can resched (no preempt count).
> + */
> +
> +static __always_inline void set_preempt_need_resched(void)
> +{
> + *preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
> +}
> +
> +static __always_inline void clear_preempt_need_resched(void)
> +{
> + *preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
> +}
> +
> +static __always_inline bool test_preempt_need_resched(void)
> +{
> + return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
> +}
> +
> #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
> extern void add_preempt_count(int val);
> extern void sub_preempt_count(int val);
> @@ -42,7 +81,7 @@ asmlinkage void preempt_schedule(void);
>
> #define preempt_check_resched() \
> do { \
> - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
> + if (unlikely(!*preempt_count_ptr())) \
> preempt_schedule(); \
> } while (0)
>
> @@ -52,7 +91,7 @@ void preempt_schedule_context(void);
>
> #define preempt_check_resched_context() \
> do { \
> - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
> + if (unlikely(!*preempt_count_ptr())) \
> preempt_schedule_context(); \
> } while (0)
> #else
> @@ -88,7 +127,6 @@ do { \
> #define preempt_enable() \
> do { \
> preempt_enable_no_resched(); \
> - barrier(); \
> preempt_check_resched(); \
> } while (0)
>
> @@ -116,7 +154,6 @@ do { \
> #define preempt_enable_notrace() \
> do { \
> preempt_enable_no_resched_notrace(); \
> - barrier(); \
> preempt_check_resched_context(); \
> } while (0)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index e783ec5..9fa151f 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -22,6 +22,7 @@ struct sched_param {
> #include <linux/errno.h>
> #include <linux/nodemask.h>
> #include <linux/mm_types.h>
> +#include <linux/preempt.h>
>
> #include <asm/page.h>
> #include <asm/ptrace.h>
> @@ -434,7 +435,9 @@ struct task_cputime {
> * We include PREEMPT_ACTIVE to avoid cond_resched() from working
> * before the scheduler is active -- see should_resched().
> */
> -#define INIT_PREEMPT_COUNT (1 + PREEMPT_ACTIVE)
> +#define INIT_PREEMPT_COUNT (1 + PREEMPT_ACTIVE + PREEMPT_NEED_RESCHED)
> +#define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED)
> +#define PREEMPT_DISABLED (1 + PREEMPT_NEED_RESCHED)
>
> /**
> * struct thread_group_cputimer - thread group interval timer counts
> @@ -2408,7 +2411,7 @@ static inline int signal_pending_state(long state, struct task_struct *p)
>
> static inline int need_resched(void)
> {
> - return unlikely(test_thread_flag(TIF_NEED_RESCHED));
> + return unlikely(test_preempt_need_resched());
> }
>
> /*
> diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
> index c261409..988573a 100644
> --- a/kernel/cpu/idle.c
> +++ b/kernel/cpu/idle.c
> @@ -105,6 +105,13 @@ static void cpu_idle_loop(void)
> __current_set_polling();
> }
> arch_cpu_idle_exit();
> + /*
> + * We need to test and propagate the TIF_NEED_RESCHED
> + * bit here because we might not have send the
> + * reschedule IPI to idle tasks.
> + */
> + if (tif_need_resched())
> + set_preempt_need_resched();
> }
> tick_nohz_idle_exit();
> schedule_preempt_disabled();
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index fe89afa..ee61f5a 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -525,8 +525,10 @@ void resched_task(struct task_struct *p)
> set_tsk_need_resched(p);
>
> cpu = task_cpu(p);
> - if (cpu == smp_processor_id())
> + if (cpu == smp_processor_id()) {
> + set_preempt_need_resched();
> return;
> + }
>
> /* NEED_RESCHED must be visible before we test polling */
> smp_mb();
> @@ -1391,6 +1393,14 @@ static void sched_ttwu_pending(void)
>
> void scheduler_ipi(void)
> {
> + /*
> + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
> + * TIF_NEED_RESCHED remotely (for the first time) will also send
> + * this IPI.
> + */
> + if (tif_need_resched())
> + set_preempt_need_resched();
> +
> if (llist_empty(&this_rq()->wake_list)
> && !tick_nohz_full_cpu(smp_processor_id())
> && !got_nohz_idle_kick())
> @@ -1714,7 +1724,7 @@ void sched_fork(struct task_struct *p)
> #endif
> #ifdef CONFIG_PREEMPT_COUNT
> /* Want to start with kernel preemption disabled. */
> - task_thread_info(p)->preempt_count = 1;
> + task_thread_info(p)->preempt_count = PREEMPT_DISABLED;
> #endif
> #ifdef CONFIG_SMP
> plist_node_init(&p->pushable_tasks, MAX_PRIO);
> @@ -2425,6 +2435,7 @@ need_resched:
> put_prev_task(rq, prev);
> next = pick_next_task(rq);
> clear_tsk_need_resched(prev);
> + clear_preempt_need_resched();
> rq->skip_clock_update = 0;
>
> if (likely(prev != next)) {
> @@ -2536,11 +2547,10 @@ EXPORT_SYMBOL(preempt_schedule);
> */
> asmlinkage void __sched preempt_schedule_irq(void)
> {
> - struct thread_info *ti = current_thread_info();
> enum ctx_state prev_state;
>
> /* Catch callers which need to be fixed */
> - BUG_ON(ti->preempt_count || !irqs_disabled());
> + BUG_ON(preempt_count() || !irqs_disabled());
>
> prev_state = exception_enter();
>
> @@ -4207,7 +4217,7 @@ void init_idle(struct task_struct *idle, int cpu)
> raw_spin_unlock_irqrestore(&rq->lock, flags);
>
> /* Set the preempt count _outside_ the spinlocks! */
> - task_thread_info(idle)->preempt_count = 0;
> + task_thread_info(idle)->preempt_count = PREEMPT_ENABLED;
>
> /*
> * The idle tasks have their own, simple scheduling class:
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists